© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13542
    Prev
    Next
    INDEX
    Explanations

    match similarity comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jobber
    -0.93
    laubt
    -0.85
    භ
    -0.83
     valide
    -0.82
    ítimo
    -0.79
     Ratios
    -0.78
    tidumbre
    -0.78
     Cookies
    -0.77
     SYMBOL
    -0.75
     galletas
    -0.75
    POSITIVE LOGITS
     matches
    1.40
     match
    1.34
     matching
    1.24
    matches
    1.20
     similarities
    1.17
    相似
    1.16
     comparing
    1.16
     Comparing
    1.16
     possible
    1.13
    match
    1.13
    Activations Density 0.067%

    No Known Activations